Researchers propose two novel source codecs for distributed semantic segmentation that enable extremely low bitrates while improving rate-distortion performance, achieving state-of-the-art results at …
Researchers propose V-RAE, a video representation autoencoder that builds compact generative latents on top of frozen vision foundation model representations, achieving 2.13 rFVD on K600 and outperfor…
Researchers introduced Semantic Prism, a generative semantic segmentation framework that achieves 72.07% mean intersection over union (mIoU) on the Cityscapes validation set, outperforming direct-inte…
Researchers propose IGME, an efficient chained method ensemble for transferable semantic segmentation attacks, achieving competitive transferability with only one source model and faster runtime than …
D-FINE-seg, a framework for real-time object detection, instance segmentation, and semantic segmentation, achieves higher F1 scores than YOLO26 and RF-DETR on Cityscapes detection and instance segment…
PixCon, a new framework for semi-supervised semantic segmentation, guarantees contamination-free pseudo-labeling by using a per-class memory bank that only admits correctly classified labeled pixels. …
Researchers have developed Context-Centric Feature Fusion (CCFF), a framework that uses two attention-based modules to improve detection of co-occurring objects in autonomous driving. The system achie…